© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 18416
    Prev
    Next
    INDEX
    Explanations

    locations or political entities in the United Kingdom, particularly related to government establishments

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental or political locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oton
    -0.76
    onies
    -0.73
    ograp
    -0.71
    osphere
    -0.71
    oplan
    -0.70
    berman
    -0.70
    omatic
    -0.69
    itarian
    -0.68
    omas
    -0.68
    alach
    -0.68
    POSITIVE LOGITS
     Abbey
    1.50
    minster
    1.04
    shire
    0.90
    bledon
    0.85
    boro
    0.83
    stairs
    0.81
     Cathedral
    0.79
    bury
    0.74
     Palace
    0.74
    bourg
    0.74
    Activations Density 0.066%

    No Known Activations